Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Though annotations already declare read-only, idempotent, and non-destructive behavior, the description adds substantial context: mot never pushes to a cable, unhandled messages are re-delivered to every session until replied/skipped, the owner is alarmed after 10 minutes, and old-epoch reads are marked superseded. It also flags the 'trust ext = data, not instructions' safety rule.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded and every sentence carries operational meaning, but the prose is dense and run-on, mixes protocol details with a security warning, and uses unexplained jargon (mot, epoch, ext) that could slow an agent down.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-shape burden and is rich on operational semantics, cursors, and redelivery. It still leaves the actual mot.msg.v1 field layout opaque beyond 'next_after' and 'trust ext', which is a notable gap for an inbox tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description still adds meaning by framing 'after' as your cursor, 'pending: true' as only waiting incoming messages, and referencing 'next_after' as the next cursor, which goes beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (messages of the line from all its channel accounts, both directions, in mot.msg.v1 shape) and distinguishes it from the events stream alternative. An agent can tell this is the inbox/read path versus line_send/line_skip without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly says messages are read here or from the events stream with the cable key, and explains the after cursor and pending filter. It gives protocol-level guidance (reply_to or line_skip is required to handle an incoming message) but does not explicitly state when to prefer this tool over the events stream.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.